> ## Documentation Index
> Fetch the complete documentation index at: https://docs.scrapeunblocker.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Ask ChatGPT and get its answer and cited sites

> Asks ChatGPT (chatgpt.com, signed out) one question and returns its finished answer: `answer` (plain text) and `answerMarkdown`, `citations` (the source pills ChatGPT attaches to claims: `position`, `siteName`, `domain`, `moreSources` - how many further sources the pill groups - and `citedText`, the answer text it backs), `links` (links written into the answer: `position`, `title`, `url`, `domain`), `sources` (every site cited or linked, once), `webSearch` (whether ChatGPT searched the web), `model` (null: signed-out ChatGPT does not show it) and `conversationId`. Signed-out ChatGPT shows the full URL of a cited page only on hover, so citations carry the site and domain, not the page URL. `country` asks from that country. Answers take 15-60 s and vary between identical calls, as they do for people. One unit per call; a 503 when ChatGPT capacity is busy is not billed.



## OpenAPI

````yaml /api-reference/openapi.json post /ai/chatgpt
openapi: 3.1.0
info:
  title: ScrapeUnblocker API
  description: >-
    Public API for the ScrapeUnblocker proxy/anti-bot service. Authenticate
    every request with the `x-scrapeunblocker-key` header. Documented here:
    page-source extraction, Google SERP scraping, image fetch, and the dedicated
    plugin endpoints (search engines, marketplaces, reviews, travel, social and
    more). All other paths exist for internal operations and are intentionally
    hidden from this spec.
  version: 3.0.0
servers:
  - url: https://api.scrapeunblocker.com
    description: Production
security: []
paths:
  /ai/chatgpt:
    post:
      tags:
        - Plugins
      summary: Ask ChatGPT and get its answer and cited sites
      description: >-
        Asks ChatGPT (chatgpt.com, signed out) one question and returns its
        finished answer: `answer` (plain text) and `answerMarkdown`, `citations`
        (the source pills ChatGPT attaches to claims: `position`, `siteName`,
        `domain`, `moreSources` - how many further sources the pill groups - and
        `citedText`, the answer text it backs), `links` (links written into the
        answer: `position`, `title`, `url`, `domain`), `sources` (every site
        cited or linked, once), `webSearch` (whether ChatGPT searched the web),
        `model` (null: signed-out ChatGPT does not show it) and
        `conversationId`. Signed-out ChatGPT shows the full URL of a cited page
        only on hover, so citations carry the site and domain, not the page URL.
        `country` asks from that country. Answers take 15-60 s and vary between
        identical calls, as they do for people. One unit per call; a 503 when
        ChatGPT capacity is busy is not billed.
      operationId: chatgpt_ai_chatgpt_post
      parameters:
        - name: prompt
          in: query
          required: true
          schema:
            type: string
            description: >-
              The question to ask ChatGPT, as a user would type it, e.g. 'best
              CRM for small business' (max 2000 characters). Each call starts a
              new conversation.
            title: Prompt
          description: >-
            The question to ask ChatGPT, as a user would type it, e.g. 'best CRM
            for small business' (max 2000 characters). Each call starts a new
            conversation.
        - name: country
          in: query
          required: false
          schema:
            anyOf:
              - type: string
              - type: 'null'
            description: >-
              Two-letter country code to ask from, e.g. US, GB, DE. ChatGPT
              tailors local results to where the visitor is. Leave blank for any
              location.
            title: Country
          description: >-
            Two-letter country code to ask from, e.g. US, GB, DE. ChatGPT
            tailors local results to where the visitor is. Leave blank for any
            location.
      responses:
        '200':
          description: JSON with ChatGPT's answer and the sites it cites.
          content:
            application/json:
              schema: {}
        '400':
          description: Invalid parameters.
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
        '502':
          description: >-
            ChatGPT gave no finished answer, refused every attempt, or did not
            answer in time.
        '503':
          description: All ChatGPT renders are busy - retry in a minute (not billed).
      security:
        - ScrapeUnblockerKey: []
components:
  schemas:
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    ScrapeUnblockerKey:
      type: apiKey
      in: header
      name: x-scrapeunblocker-key
      description: Your ScrapeUnblocker API key. Apply on every request.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.